[ { "input_cost_per_token": 8e-9, "output_cost_per_token": 0, "max_input_tokens": 512, "output_vector_size": 768, "model_id": "baai/bge-base-en-v1.5", "model_name": "Bge Base En V1.5", "provider_id": "together", "provider_name": "Together AI", "max_output_tokens": 0, "input_cost_per_million": 0.008, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 8e-9, "output_cost_per_token": 0, "max_input_tokens": 512, "output_vector_size": 768, "model_id": "BAAI/bge-base-en-v1.5", "model_name": "Bge Base En V1.5", "provider_id": "together", "provider_name": "Together AI", "max_output_tokens": 0, "input_cost_per_million": 0.008, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000007, "max_input_tokens": 128000, "max_output_tokens": 20480, "max_tokens": 20480, "supports_tool_choice": true, "model_id": "deepseek-ai/DeepSeek-R1", "model_name": "DeepSeek R1", "provider_id": "together", "provider_name": "Together AI", "input_cost_per_million": 3, "output_cost_per_million": 7, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true, "supports_vision": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 5.5e-7, "output_cost_per_token": 0.00000219, "max_input_tokens": 128000, "source": "https://www.together.ai/models/deepseek-r1-0528-throughput", "supports_tool_choice": true, "model_id": "deepseek-ai/DeepSeek-R1-0528-tput", "model_name": "DeepSeek R1 0528 Tput", "provider_id": "together", "provider_name": "Together AI", "max_output_tokens": 0, "input_cost_per_million": 0.55, "output_cost_per_million": 2.1900000000000004, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true, "supports_vision": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00000125, "max_input_tokens": 65536, "max_output_tokens": 8192, "max_tokens": 8192, "supports_tool_choice": true, "model_id": "deepseek-ai/DeepSeek-V3", "model_name": "DeepSeek V3", "provider_id": "together", "provider_name": "Together AI", "input_cost_per_million": 1.25, "output_cost_per_million": 1.25, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true, "supports_vision": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000017, "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "source": "https://www.together.ai/models/deepseek-v3-1", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "deepseek-ai/DeepSeek-V3.1", "model_name": "DeepSeek V3.1", "provider_id": "together", "provider_name": "Together AI", "input_cost_per_million": 0.6, "output_cost_per_million": 1.7, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "model_id": "meta-llama/Llama-3.2-3B-Instruct-Turbo", "model_name": "Llama 3.2 3B Instruct Turbo", "provider_id": "together", "provider_name": "Together AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true, "supports_vision": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 8.8e-7, "output_cost_per_token": 8.8e-7, "supports_tool_choice": true, "model_id": "meta-llama/Llama-3.3-70B-Instruct-Turbo", "model_name": "Llama 3.3 70B Instruct Turbo", "provider_id": "together", "provider_name": "Together AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.88, "output_cost_per_million": 0.88, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true, "supports_vision": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 0, "output_cost_per_token": 0, "supports_tool_choice": true, "model_id": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free", "model_name": "Llama 3.3 70B Instruct Turbo Free", "provider_id": "together", "provider_name": "Together AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true, "supports_vision": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 2.7e-7, "output_cost_per_token": 8.5e-7, "supports_tool_choice": true, "model_id": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8", "model_name": "Llama 4 Maverick 17B 128E Instruct FP8", "provider_id": "together", "provider_name": "Together AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.27, "output_cost_per_million": 0.85, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true, "supports_vision": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 1.8e-7, "output_cost_per_token": 5.9e-7, "supports_tool_choice": true, "model_id": "meta-llama/Llama-4-Scout-17B-16E-Instruct", "model_name": "Llama 4 Scout 17B 16E Instruct", "provider_id": "together", "provider_name": "Together AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.18, "output_cost_per_million": 0.59, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true, "supports_vision": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 0.0000035, "output_cost_per_token": 0.0000035, "supports_tool_choice": true, "model_id": "meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo", "model_name": "Meta Llama 3.1 405B Instruct Turbo", "provider_id": "together", "provider_name": "Together AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 3.5, "output_cost_per_million": 3.5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true, "supports_vision": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 8.8e-7, "output_cost_per_token": 8.8e-7, "supports_tool_choice": true, "model_id": "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo", "model_name": "Meta Llama 3.1 70B Instruct Turbo", "provider_id": "together", "provider_name": "Together AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.88, "output_cost_per_million": 0.88, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true, "supports_vision": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 1.8e-7, "output_cost_per_token": 1.8e-7, "supports_tool_choice": true, "model_id": "meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo", "model_name": "Meta Llama 3.1 8B Instruct Turbo", "provider_id": "together", "provider_name": "Together AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.18, "output_cost_per_million": 0.18, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true, "supports_vision": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "model_id": "mistralai/Mistral-7B-Instruct-v0.1", "model_name": "Mistral 7B Instruct V0.1", "provider_id": "together", "provider_name": "Together AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true, "supports_vision": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "model_id": "mistralai/Mistral-Small-24B-Instruct-2501", "model_name": "Mistral Small 24B Instruct (Jan 2025)", "provider_id": "together", "provider_name": "Together AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 6e-7, "supports_tool_choice": true, "model_id": "mistralai/Mixtral-8x7B-Instruct-v0.1", "model_name": "Mixtral 8x7B Instruct V0.1", "provider_id": "together", "provider_name": "Together AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.6, "output_cost_per_million": 0.6, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true, "supports_vision": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000003, "source": "https://www.together.ai/models/kimi-k2-instruct", "supports_tool_choice": true, "model_id": "moonshotai/Kimi-K2-Instruct", "model_name": "Kimi K2 Instruct", "provider_id": "together", "provider_name": "Together AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 1, "output_cost_per_million": 3, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true, "supports_vision": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000003, "max_input_tokens": 262144, "source": "https://www.together.ai/models/kimi-k2-0905", "supports_tool_choice": true, "model_id": "moonshotai/Kimi-K2-Instruct-0905", "model_name": "Kimi K2 Instruct (May 2009)", "provider_id": "together", "provider_name": "Together AI", "max_output_tokens": 0, "input_cost_per_million": 1, "output_cost_per_million": 3, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000028, "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "source": "https://www.together.ai/models/kimi-k2-5", "supports_tool_choice": true, "supports_reasoning": true, "model_id": "moonshotai/Kimi-K2.5", "model_name": "Kimi K2.5", "provider_id": "together", "provider_name": "Together AI", "input_cost_per_million": 0.5, "output_cost_per_million": 2.8, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://www.together.ai/models/gpt-oss-120b", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "openai/gpt-oss-120b", "model_name": "GPT Oss 120B", "provider_id": "together", "provider_name": "Together AI", "input_cost_per_million": 0.15, "output_cost_per_million": 0.6, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true, "supports_vision": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 5e-8, "output_cost_per_token": 2e-7, "max_input_tokens": 128000, "source": "https://www.together.ai/models/gpt-oss-20b", "supports_tool_choice": true, "model_id": "openai/gpt-oss-20b", "model_name": "GPT Oss 20B", "provider_id": "together", "provider_name": "Together AI", "max_output_tokens": 0, "input_cost_per_million": 0.049999999999999996, "output_cost_per_million": 0.19999999999999998, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true, "supports_vision": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "model_id": "Qwen/Qwen2.5-72B-Instruct-Turbo", "model_name": "Qwen2.5 72B Instruct Turbo", "provider_id": "together", "provider_name": "Together AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true, "supports_vision": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "model_id": "Qwen/Qwen2.5-7B-Instruct-Turbo", "model_name": "Qwen2.5 7B Instruct Turbo", "provider_id": "together", "provider_name": "Together AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true, "supports_vision": false }, { "supports_function_calling": false, "supports_parallel_function_calling": false, "input_cost_per_token": 2e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 40000, "source": "https://www.together.ai/models/qwen3-235b-a22b-fp8-tput", "supports_tool_choice": false, "model_id": "Qwen/Qwen3-235B-A22B-fp8-tput", "model_name": "Qwen3 235B A22B Fp8 Tput", "provider_id": "together", "provider_name": "Together AI", "max_output_tokens": 0, "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 0.6, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": false, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 0.000006, "max_input_tokens": 262000, "source": "https://www.together.ai/models/qwen3-235b-a22b-instruct-2507-fp8", "supports_tool_choice": true, "model_id": "Qwen/Qwen3-235B-A22B-Instruct-2507-tput", "model_name": "Qwen3 235B A22B Instruct 2507 Tput", "provider_id": "together", "provider_name": "Together AI", "max_output_tokens": 0, "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 6, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true, "supports_vision": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 6.5e-7, "output_cost_per_token": 0.000003, "max_input_tokens": 256000, "source": "https://www.together.ai/models/qwen3-235b-a22b-thinking-2507", "supports_tool_choice": true, "model_id": "Qwen/Qwen3-235B-A22B-Thinking-2507", "model_name": "Qwen3 235B A22B Thinking (Jul 2025)", "provider_id": "together", "provider_name": "Together AI", "max_output_tokens": 0, "input_cost_per_million": 0.65, "output_cost_per_million": 3, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true, "supports_vision": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000002, "max_input_tokens": 256000, "source": "https://www.together.ai/models/qwen3-coder-480b-a35b-instruct", "supports_tool_choice": true, "model_id": "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8", "model_name": "Qwen3 Coder 480B A35B Instruct FP8", "provider_id": "together", "provider_name": "Together AI", "max_output_tokens": 0, "input_cost_per_million": 2, "output_cost_per_million": 2, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true, "supports_vision": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 0.0000015, "max_input_tokens": 262144, "source": "https://www.together.ai/models/qwen3-next-80b-a3b-instruct", "supports_tool_choice": true, "model_id": "Qwen/Qwen3-Next-80B-A3B-Instruct", "model_name": "Qwen3 Next 80B A3B Instruct", "provider_id": "together", "provider_name": "Together AI", "max_output_tokens": 0, "input_cost_per_million": 0.15, "output_cost_per_million": 1.5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true, "supports_vision": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 0.0000015, "max_input_tokens": 262144, "source": "https://www.together.ai/models/qwen3-next-80b-a3b-thinking", "supports_tool_choice": true, "model_id": "Qwen/Qwen3-Next-80B-A3B-Thinking", "model_name": "Qwen3 Next 80B A3B Thinking", "provider_id": "together", "provider_name": "Together AI", "max_output_tokens": 0, "input_cost_per_million": 0.15, "output_cost_per_million": 1.5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true, "supports_vision": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000036, "max_input_tokens": 262144, "source": "https://www.together.ai/models/Qwen/Qwen3.5-397B-A17B", "supports_tool_choice": true, "model_id": "Qwen/Qwen3.5-397B-A17B", "model_name": "Qwen3.5 397B A17B", "provider_id": "together", "provider_name": "Together AI", "max_output_tokens": 0, "input_cost_per_million": 0.6, "output_cost_per_million": 3.5999999999999996, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true, "supports_vision": false }, { "input_cost_per_token": 8e-7, "output_cost_per_token": 8e-7, "model_id": "together-ai-21.1b-41b", "model_name": "Together AI 21.1B 41B", "provider_id": "together", "provider_name": "Together AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.7999999999999999, "output_cost_per_million": 0.7999999999999999, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "model_id": "together-ai-4.1b-8b", "model_name": "Together AI 4.1B 8B", "provider_id": "together", "provider_name": "Together AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 0.19999999999999998, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "model_id": "together-ai-41.1b-80b", "model_name": "Together AI 41.1B 80B", "provider_id": "together", "provider_name": "Together AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.8999999999999999, "output_cost_per_million": 0.8999999999999999, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 3e-7, "output_cost_per_token": 3e-7, "max_tokens": 1000, "model_id": "together-ai-8.1b-21b", "model_name": "Together AI 8.1B 21B", "provider_id": "together", "provider_name": "Together AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.3, "output_cost_per_million": 0.3, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.0000018, "output_cost_per_token": 0.0000018, "model_id": "together-ai-81.1b-110b", "model_name": "Together AI 81.1B 110B", "provider_id": "together", "provider_name": "Together AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 1.7999999999999998, "output_cost_per_million": 1.7999999999999998, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1.6e-8, "output_cost_per_token": 0, "model_id": "together-ai-embedding-151m-to-350m", "model_name": "Together AI Embedding 151m To 350m", "provider_id": "together", "provider_name": "Together AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.016, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 8e-9, "output_cost_per_token": 0, "model_id": "together-ai-embedding-up-to-150m", "model_name": "Together AI Embedding Up To 150m", "provider_id": "together", "provider_name": "Together AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.008, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7, "model_id": "together-ai-up-to-4b", "model_name": "Together AI Up To 4B", "provider_id": "together", "provider_name": "Together AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.09999999999999999, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "model_id": "togethercomputer/CodeLlama-34b-Instruct", "model_name": "CodeLlama 34B Instruct", "provider_id": "together", "provider_name": "Together AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 0.0000011, "max_input_tokens": 128000, "source": "https://www.together.ai/models/glm-4-5-air", "supports_tool_choice": true, "model_id": "zai-org/GLM-4.5-Air-FP8", "model_name": "GLM 4.5 Air FP8", "provider_id": "together", "provider_name": "Together AI", "max_output_tokens": 0, "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 1.1, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true, "supports_vision": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000022, "max_input_tokens": 200000, "max_output_tokens": 200000, "max_tokens": 200000, "source": "https://www.together.ai/models/glm-4-6", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "zai-org/GLM-4.6", "model_name": "GLM 4.6", "provider_id": "together", "provider_name": "Together AI", "input_cost_per_million": 0.6, "output_cost_per_million": 2.2, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 4.5e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 200000, "max_output_tokens": 200000, "max_tokens": 200000, "source": "https://www.together.ai/models/glm-4-7", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "zai-org/GLM-4.7", "model_name": "GLM 4.7", "provider_id": "together", "provider_name": "Together AI", "input_cost_per_million": 0.44999999999999996, "output_cost_per_million": 2, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false } ]